1 |
Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extraction ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Cross-lingual Representation Learning for Natural Language Processing
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions? ...
|
|
|
|
Abstract:
Is it possible to use natural language to intervene in a model's behavior and alter its prediction in a desired way? We investigate the effectiveness of natural language interventions for reading-comprehension systems, studying this in the context of social stereotypes. Specifically, we propose a new language understanding task, Linguistic Ethical Interventions (LEI), where the goal is to amend a question-answering (QA) model's unethical behavior by communicating context-specific principles of ethics and equity to it. To this end, we build upon recent methods for quantifying a system's social stereotypes, augmenting them with different kinds of ethical interventions and the desired model behavior under such interventions. Our zero-shot evaluation finds that even today's powerful neural language models are extremely poor ethical-advice takers, that is, they respond surprisingly little to ethical interventions even though these interventions are stated as simple sentences. Few-shot learning improves model ... : 9 pages, Findings of ACL-IJCNLP 2021 ...
|
|
Keyword:
Artificial Intelligence cs.AI; Computation and Language cs.CL; FOS Computer and information sciences; Machine Learning cs.LG
|
|
URL: https://arxiv.org/abs/2106.01465 https://dx.doi.org/10.48550/arxiv.2106.01465
|
|
BASE
|
|
Hide details
|
|
4 |
Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Training ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Societal Biases in Language Generation: Progress and Challenges ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Socially Aware Bias Measurements for Hindi Language Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Intent Classification and Slot Filling for Privacy Policies ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions? ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Defense against Synonym Substitution-based Adversarial Attacks via Dirichlet Neighborhood Ensemble ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Training ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Syntax-augmented Multilingual BERT for Cross-lingual Transfer ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Syntax-augmented Multilingual BERT for Cross-lingual Transfer ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
"The Boating Store Had Its Best Sail Ever": Pronunciation-attentive Contextualized Pun Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
On the Robustness of Language Encoders against Grammatical Errors ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
GATE: Graph Attention Transformer Encoder for Cross-lingual Relation and Event Extraction ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|